© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 91827
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "reporting" related to documentation and data reporting practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    reporting and related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ever
    -0.43
    веро
    -0.42
    Ever
    -0.40
     Ever
    -0.39
    isEqualTo
    -0.38
    clientX
    -0.38
    sma
    -0.37
    Gu
    -0.37
    yandex
    -0.37
     kema
    -0.37
    POSITIVE LOGITS
     reporting
    0.88
     Reporting
    0.86
    Reporting
    0.81
    reporting
    0.77
     REPORTING
    0.75
     report
    0.73
    report
    0.71
     pinulongan
    0.69
     otomatig
    0.68
     المعيارى
    0.66
    Activations Density 0.006%

    No Known Activations